implement-quick

Executes one bounded code change from an ephemeral brief with verification checks.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/skyrocoster/dnd-kids-resources --skill implement-quick-skyrocoster
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: implement-quick
Source: https://github.com/skyrocoster/dnd-kids-resources/tree/main/.opencode/skills/implement-quick
Command: npx skills add https://github.com/skyrocoster/dnd-kids-resources --skill implement-quick-skyrocoster

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents scope creep and uncontrolled edits when an AI agent makes small code changes by enforcing a strict brief with authorized paths, pre-verified facts, and a hard stop after verification. ## Core Features & Use Cases - Bounded Execution: Works only inside AUTHORIZED PATHS, trusting KNOWN FACTS without re-exploration, and makes exactly the one CHANGE requested. - Verification Gate: Runs the CHECK commands as written, allows one repair attempt, and stops after two failed verification runs. - Escalation Discipline: Stops and reports instead of improvising when scope grows, a KNOWN FACT is wrong, or the work needs a full plan or work order. - Use Case: A coordinator hands the agent a brief to rename a function in two specified files and run the test suite; the agent makes only that edit, runs the tests, reports the result, and stops. ## Quick Start Hand the agent a quick-executor brief containing GOAL, AUTHORIZED PATHS, KNOWN FACTS, CHANGE, CHECK, and ESCALATE IF sections and ask it to implement the single change.

Frequently Asked Questions about implement-quick

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a single bounded code change with an AI agent?▼

Provide a brief with GOAL, AUTHORIZED PATHS, KNOWN FACTS, CHANGE, CHECK, and ESCALATE IF sections. The agent makes only that change inside the listed paths, runs the check commands, and stops once they pass.

What is the difference between a quick-executor brief and a work order?▼

A brief is ephemeral and covers exactly one focused change with no plan file, status tracking, or deviation bookkeeping. Work that needs a plan, multiple changes, or a contract-level modification belongs on the plan-to-work-order path instead.

What happens when the verification check fails twice?▼

After two failed verification runs the agent stops and reports instead of continuing to iterate. The harness blocks further implementation and checks, and the coordinator decides the next step.

When should the agent escalate instead of completing the change?▼

Escalation is required when the change needs files outside AUTHORIZED PATHS, scope grows beyond one change, a KNOWN FACT proves wrong, or the work needs a full plan. The agent leaves partial work in place and reports exactly what it saw.

Can the agent refactor nearby code while making the change?▼

No. The instructions require the smallest change that meets the goal, matching existing style, with no refactoring, renaming, or improvements to code outside the requested change.